Relating weapon system test sizes to warfighting capability

Military planners use weapon system reliability estimates in creating and evaluating war plans. The accuracy of these estimates is important to ensure our military forces are efficiently planned and effectively employed. Results of annual weapon system flight tests are used by military planners to validate the accuracy and confidence of these reliability estimates. Since each test is expensive, the military needs to trade off the cost of the additional tests against the improved accuracy and confidence of the reliability estimate. Classical statistical approaches that are currently used obfuscate the impact of various testing rates. Gallagher, Weir, and True suggest that the number of tests be determined with regard to the military impact. Using Bayesian statistics they calculate the expected additional weapons lost, given that a reliability degrade of unknown magnitude remains undetected. This methodology allows decision makers and planners alike to assess the impact of a possible weapon system reliability degrade to their war plans.